YOLOv6

<p align="center"> <img src="assets/banner-YOLO.png" align="middle" width = "1000" /> </p>

English | 简体中文

<br> <div> </a> <a href="https://colab.research.google.com/github/meituan/YOLOv6/blob/main/turtorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> <a href="https://www.kaggle.com/code/housanduo/yolov6"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open In Kaggle"></a> </div> <br>

YOLOv6

Implementation of paper:

• YOLOv6 v3.0: A Full-Scale Reloading 🔥
• YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications

<p align="center"> <img src="assets/speed_comparision_v3.png" align="middle" width = "1000" /> </p>

What's New

• [2023.09.15] Release YOLOv6-Segmentation. 🚀 Performance
• [2023.04.28] Release YOLOv6Lite models on mobile or CPU. ⭐️ Mobile Benchmark
• [2023.03.10] Release YOLOv6-Face. 🔥 Performance
• [2023.03.02] Update base models to version 3.0.
• [2023.01.06] Release P6 models and enhance the performance of P5 models. ⭐️ Benchmark
• [2022.11.04] Release base models to simplify the training and deployment process.
• [2022.09.06] Customized quantization methods. 🚀 Quantization Tutorial
• [2022.09.05] Release M/L models and update N/T/S models with enhanced performance.
• [2022.06.23] Release N/T/S models with excellent performance.

Benchmark

| Model | Size | mAP<sup>val<br/>0.5:0.95 | Speed<sup>T4<br/>trt fp16 b1 <br/>(fps) | Speed<sup>T4<br/>trt fp16 b32 <br/>(fps) | Params<br/><sup> (M) | FLOPs<br/><sup> (G) | | :----------------------------------------------------------- | ---- | :----------------------- | --------------------------------------- | ---------------------------------------- | -------------------- | ------------------- | | YOLOv6-N | 640 | 37.5 | 779 | 1187 | 4.7 | 11.4 | | YOLOv6-S | 640 | 45.0 | 339 | 484 | 18.5 | 45.3 | | YOLOv6-M | 640 | 50.0 | 175 | 226 | 34.9 | 85.8 | | YOLOv6-L | 640 | 52.8 | 98 | 116 | 59.6 | 150.7 | | | | | | | | YOLOv6-N6 | 1280 | 44.9 | 228 | 281 | 10.4 | 49.8 | | YOLOv6-S6 | 1280 | 50.3 | 98 | 108 | 41.4 | 198.0 | | YOLOv6-M6 | 1280 | 55.2 | 47 | 55 | 79.6 | 379.5 | | YOLOv6-L6 | 1280 | 57.2 | 26 | 29 | 140.4 | 673.4 |

<details> <summary>Table Notes</summary>

• All checkpoints are trained with self-distillation except for YOLOv6-N6/S6 models trained to 300 epochs without distillation.
• Results of the mAP and speed are evaluated on COCO val2017 dataset with the input resolution of 640×640 for P5 models and 1280x1280 for P6 models.
• Speed is tested with TensorRT 7.2 on T4.
• Refer to Test speed tutorial to reproduce the speed results of YOLOv6.
• Params and FLOPs of YOLOv6 are estimated on deployed models.

</details> <details> <summary>Legacy models</summary>

| Model | Size | mAP<sup>val<br/>0.5:0.95 | Speed<sup>T4<br/>trt fp16 b1 <br/>(fps) | Speed<sup>T4<br/>trt fp16 b32 <br/>(fps) | Params<br/><sup> (M) | FLOPs<br/><sup> (G) | | :----------------------------------------------------------- | ---- | :------------------------------------ | --------------------------------------- | ---------------------------------------- | -------------------- | ------------------- | | YOLOv6-N | 640 | 35.9^300e<br/>36.3<sup>400e | 802 | 1234 | 4.3 | 11.1 | | YOLOv6-T | 640 | 40.3^300e<br/>41.1<sup>400e | 449 | 659 | 15.0 | 36.7 | | YOLOv6-S | 640 | 43.5^300e<br/>43.8<sup>400e | 358 | 495 | 17.2 | 44.2 | | YOLOv6-M | 640 | 49.5 | 179 | 233 | 34.3 | 82.2 | | YOLOv6-L-ReLU | 640 | 51.7 | 113 | 149 | 58.5 | 144.0 | | YOLOv6-L | 640 | 52.5 | 98 | 121 | 58.5 | 144.0 |

• Speed is tested with TensorRT 7.2 on T4.

Quantized model 🚀

| Model | Size | Precision | mAP<sup>val<br/>0.5:0.95 | Speed<sup>T4<br/>trt b1 <br/>(fps) | Speed<sup>T4<br/>trt b32 <br/>(fps) | | :-------------------- | ---- | --------- | :----------------------- | ---------------------------------- | ----------------------------------- | | YOLOv6-N RepOpt | 640 | INT8 | 34.8 | 1114 | 1828 | | YOLOv6-N | 640 | FP16 | 35.9 | 802 | 1234 | | YOLOv6-T RepOpt | 640 | INT8 | 39.8 | 741 | 1167 | | YOLOv6-T | 640 | FP16 | 40.3 | 449 | 659 | | YOLOv6-S RepOpt | 640 | INT8 | 43.3 | 619 | 924 | | YOLOv6-S | 640 | FP16 | 43.5 | 377 | 541 |

• Speed is tested with TensorRT 8.4 on T4.
• Precision is figured on models for 300 epochs.

</details>

Mobile Benchmark

| Model | Size | mAP<sup>val<br/>0.5:0.95 | sm8350<br/><sup>(ms) | mt6853<br/><sup>(ms) | sdm660<br/><sup>(ms) |Params<br/><sup> (M) | FLOPs<br/><sup> (G) | | :----------------------------------------------------------- | ---- | -------------------- | -------------------- | -------------------- | -------------------- | -------------------- | -------------------- | | YOLOv6Lite-S | 320320 | 22.4 | 7.99 | 11.99 | 41.86 | 0.55 | 0.56 | | YOLOv6Lite-M | 320320 | 25.1 | 9.08 | 13.27 | 47.95 | 0.79 | 0.67 | | YOLOv6Lite-L | 320320 | 28.0 | 11.37 | 16.20 | 61.40 | 1.09 | 0.87 | | YOLOv6Lite-L | 320192 | 25.0 | 7.02 | 9.66 | 36.13 |